Publications


03/30/2022

On the Question of Rediscovering Drug Molecules

In conversations with people outside Norachem, the most common enquiry is whether the platform can rediscover a known drug. An intriguing question — since it is often accompanied by the belief that by doing so, Norachem would provide renewed validation of its generative design paradigm. So, we decided to run simulations to prove Norachem’s capabilities in this regard…


09/02/2021

On the Shortcomings of Continuous Representations of Chemical Space

The paper (Gomez-Bombarelli et al., 2018), which introduces Chemical VAE and provides the exploratory technique for the GENTRL model described in (Zhavoronkov et al., 2019), makes a few stark claims in its introduction. We quote an excerpt here: “…computational molecular design is limited by the search strategy used to explore chemical space. Current methods either exhaustively search through a fixed library, or use discrete local search methods such as genetic algorithms or similar discrete interpolation techniques…


05/31/2021

Generative Design for De Novo Drugs

Recent years have seen a surge in the use of computational methods to design de novo drugs. In most instances, the computation has consisted entirely of using predictive modelling to screen a chemical library to identify potent compounds. This approach towards drug discovery has several shortcomings…